Lightweight high-performance pose recognition network: HR-LiteNet

Zhiming Cai; Liping Zhuang; Jin Chen; Jinhua Jiang; Zhiming Cai; Liping Zhuang; Jin Chen; Jinhua Jiang

doi:10.3934/era.2024055

Electronic Research Archive

2024, Volume 32, Issue 2: 1145-1159. doi: 10.3934/era.2024055

Previous Article Next Article

Research article Special Issues

Lightweight high-performance pose recognition network: HR-LiteNet

1.
School of Electronics, Electrical Engineering and Physics, Fujian University of Technology, Fuzhou 350118, China
2.
National Demonstration Center for Experimental Electronic Information and Electrical Technology Education, Fujian University of Technology, Fuzhou 350118, China

Received: 16 October 2023 Revised: 27 December 2023 Accepted: 11 January 2024 Published: 29 January 2024

To address the limited resources of mobile devices and embedded platforms, we propose a lightweight pose recognition network named HR-LiteNet. Built upon a high-resolution architecture, the network incorporates depthwise separable convolutions, Ghost modules, and the Convolutional Block Attention Module to construct L_block and L_basic modules, aiming to reduce network parameters and computational complexity while maintaining high accuracy. Experimental results demonstrate that on the MPII validation dataset, HR-LiteNet achieves an accuracy of 83.643% while reducing the parameter count by approximately 26.58 M and lowering computational complexity by 8.04 GFLOPs compared to the HRNet network. Moreover, HR-LiteNet outperforms other lightweight models in terms of parameter count and computational requirements while maintaining high accuracy. This design provides a novel solution for pose recognition in resource-constrained environments, striking a balance between accuracy and lightweight demands.
- human pose estimation,
- high-resolution network,
- Ghost,
- lightweight module
Citation: Zhiming Cai, Liping Zhuang, Jin Chen, Jinhua Jiang. Lightweight high-performance pose recognition network: HR-LiteNet[J]. Electronic Research Archive, 2024, 32(2): 1145-1159. doi: 10.3934/era.2024055

Related Papers:

Abstract

To address the limited resources of mobile devices and embedded platforms, we propose a lightweight pose recognition network named HR-LiteNet. Built upon a high-resolution architecture, the network incorporates depthwise separable convolutions, Ghost modules, and the Convolutional Block Attention Module to construct L_block and L_basic modules, aiming to reduce network parameters and computational complexity while maintaining high accuracy. Experimental results demonstrate that on the MPII validation dataset, HR-LiteNet achieves an accuracy of 83.643% while reducing the parameter count by approximately 26.58 M and lowering computational complexity by 8.04 GFLOPs compared to the HRNet network. Moreover, HR-LiteNet outperforms other lightweight models in terms of parameter count and computational requirements while maintaining high accuracy. This design provides a novel solution for pose recognition in resource-constrained environments, striking a balance between accuracy and lightweight demands.

References

[1]	S. Wu, Z. Wang, B. Shen, J. Wang, D. Li, Human-computer interaction based on machine vision of a smart assembly workbench, Assem. Autom., 40 (2020), 475–482. https://doi.org/10.1108/AA-10-2018-0170 doi: 10.1108/AA-10-2018-0170
[2]	B. Debnath, M. O'brien, M. Yamaguchi, A. Behera, A review of computer vision-based approaches for physical rehabilitation and assessment, Multimedia Syst., 28 (2022), 209–239. https://doi.org/10.1007/s00530-021-00815-4 doi: 10.1007/s00530-021-00815-4
[3]	N. Lyons, Deep learning-based computer vision algorithms, immersive analytics and simulation software, and virtual reality modeling tools in digital twin-driven smart manufacturing, Econ. Manage. Financ. Mark., 17 (2022), 67–81. https://doi.org/10.22381/emfm17220224 doi: 10.22381/emfm17220224
[4]	Q. Kha, Q. Ho, N. Q. K. Le, Identifying snare proteins using an alignment-free method based on multiscan convolutional neural network and PSSM profiles, J. Chem. Inf. Model., 62 (2022), 4820–4826. https://doi.org/10.1021/acs.jcim.2c01034 doi: 10.1021/acs.jcim.2c01034
[5]	Z. Zhao, J. Gui, A. Yao, N. Q. K. Le, M. C. H. Chua, Improved prediction model of protein and peptide toxicity by integrating channel attention into a convolutional neural network and gated recurrent units, ACS Omega, 7 (2022), 40569–40577. https://doi.org/10.1021/acsomega.2c05881 doi: 10.1021/acsomega.2c05881
[6]	Z. Li, F. Liu, W. Yang, S. Peng, J. Zhou, A survey of convolutional neural networks: analysis, applications, and prospects, IEEE Trans. Neural Networks Learn. Syst., 33 (2022), 6999–7019. https://doi.org/10.1109/TNNLS.2021.3084827 doi: 10.1109/TNNLS.2021.3084827
[7]	C. Zheng, S. Zhu, M. Mendieta, T. Yang, C. Chen, Z. Ding, 3D human pose estimation with spatial and temporal transformers, preprint, arXiv: 2103.10455.
[8]	C. Li, G. H. Lee, Generating multiple hypotheses for 3D human pose estimation with mixture density network, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), 9879–9887. https://doi.org/10.1109/CVPR.2019.01012
[9]	A. Toshev, C. Szegedy, Deeppose: Human pose estimation via deep neural networks, in 2014 IEEE Conference on Computer Vision and Pattern Recognition, (2014), 1653–1660. https://doi.org/10.1109/CVPR.2014.214
[10]	J. Tompson, A. Jain, Y. LeCun, C. Bregler, Joint training of a convolutional network and a graphical model for human pose estimation, preprint, arXiv: 1406.2984.
[11]	S. Wei, V. Ramakrishna, T. Kanade, Y. Sheikh, Convolutional pose machines, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2016), 4724–4732. https://doi.org/10.1109/CVPR.2016.511
[12]	Y. Chen, Y. Tian, M. He, Monocular human pose estimation: A survey of deep learning-based methods, Comput. Vision Image Understanding, 192 (2020), 102897. https://doi.org/10.1016/j.cviu.2019.102897 doi: 10.1016/j.cviu.2019.102897
[13]	C. Zheng, W. Wu, C. Chen, T. Yang, S. Zhu, J. Shen, et al., Deep learning-based human pose estimation: A survey, ACM Comput. Surv., 56 (2023), 1–37. https://doi.org/10.1145/3603618 doi: 10.1145/3603618
[14]	G. Papandreou, T. Zhu, N. Kanazawa, A. Toshev, J. Tompson, C. Bregler, et al., Towards accurate multi-person pose estimation in the wild, in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017), 4903–4911. https://doi.org/10.1109/CVPR.2017.395
[15]	S. Ren, K. He, R. Girshick, J. Sun, Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Trans. Pattern Anal. Mach. Intell., 39 (2017), 1137–1149. https://doi.org/10.1109/tpami.2016.2577031 doi: 10.1109/tpami.2016.2577031
[16]	K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2016), 770–778. https://doi.org/10.1109/CVPR.2016.90
[17]	K. Sun, B. Xiao, D. Liu, J. Wang, Deep high-resolution representation learning for human pose estimation, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), 5693–5703. https://doi.org/10.1109/CVPR.2019.00584
[18]	L. Pishchulin, E. Insafutdinov, S. Tang, B. Andres, M. Andriluka, P. Gehler, et al., Deepcut: Joint subset partition and labeling for multi person pose estimation, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2016), 4929–4937. https://doi.org/10.1109/CVPR.2016.533
[19]	Z. Cao, T. Simon, S. Wei, Y. Sheikh, Realtime multi-person 2D pose estimation using part affinity fields, in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017), 1302–1310. https://doi.org/10.1109/CVPR.2017.143
[20]	F. Zhang, X. Zhu, M. Ye, Fast human pose estimation, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), 3512–3521. https://doi.org/10.1109/CVPR.2019.00363
[21]	D. Xu, R. Zhang, L. Guo, C. Feng, S. Gao, LDNet: Lightweight dynamic convolution network for human pose estimation, Adv. Eng. Inf., 54 (2022), 101785. https://doi.org/10.1016/j.aei.2022.101785 doi: 10.1016/j.aei.2022.101785
[22]	C. Yu, B. Xiao, C. Gao, L. Yuan, L. Zhang, N. Sang, et al., Lite-HRNet: A lightweight high-resolution network, in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2021), 10435–10445. https://doi.org/10.1109/CVPR46437.2021.01030
[23]	S. Woo, J. Park, J. Lee, I. S. Kweon, Cbam: Convolutional block attention module, in European Conference on Computer Vision, 11211 (2018), 3–19. https://doi.org/10.1007/978-3-030-01234-2_1
[24]	A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, et al., MobileNets: Efficient convolutional neural networks for mobile vision applications, preprint, arXiv: 1704.04861.
[25]	K. Han, Y. Wang, Q. Tian, J. Guo, C. Xu, C. Xu, Ghostnet: More features from cheap operations, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2020), 1577–1586. https://doi.org/10.1109/CVPR42600.2020.00165
[26]	M. Andriluka, L. Pishchulin, P. Gehler, B. Schiele, 2D human pose estimation: New benchmark and state of the art analysis, in 2014 IEEE Conference on Computer Vision and Pattern Recognition, (2014), 3686–3693. https://doi.org/10.1109/CVPR.2014.471
[27]	N. Ma, X. Zhang, H. Zheng, J. Sun, Shufflenet v2: Practical guidelines for efficient cnn architecture design, in European Conference on Computer Vision, 11218 (2018), 122–138. https://doi.org/10.1007/978-3-030-01264-9_8
[28]	M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L. Chen, Mobilenetv2: Inverted residuals and linear bottlenecks, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2018), 4510–4520. https://doi.org/10.1109/CVPR.2018.00474
[29]	M Tan, Q. V. Le, Efficientnet: Rethinking model scaling for convolutional neural networks, preprint, arXiv: 1905.11946.

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)